{"id":"https://openalex.org/W4220793814","doi":"https://doi.org/10.1145/3490099.3511164","title":"BeParrot: Efficient Interface for Transcribing Unclear Speech via Respeaking","display_name":"BeParrot: Efficient Interface for Transcribing Unclear Speech via Respeaking","publication_year":2022,"publication_date":"2022-03-21","ids":{"openalex":"https://openalex.org/W4220793814","doi":"https://doi.org/10.1145/3490099.3511164"},"language":"en","primary_location":{"id":"doi:10.1145/3490099.3511164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3490099.3511164","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3490099.3511164","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"27th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3490099.3511164","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044514558","display_name":"Riku Arakawa","orcid":"https://orcid.org/0000-0001-7868-4754"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Riku Arakawa","raw_affiliation_strings":["Human-Computer Interaction Institute, Carnegie Mellon University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human-Computer Interaction Institute, Carnegie Mellon University, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051687457","display_name":"Hiromu Yakura","orcid":"https://orcid.org/0000-0002-2558-735X"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]},{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiromu Yakura","raw_affiliation_strings":["University of Tsukuba, Japan and National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Japan and National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I146399215","https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5534,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5836774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"832","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8350245952606201},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7372204065322876},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6050679683685303},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5589120388031006},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.5560511946678162},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5501837730407715},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.49196740984916687},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.49116751551628113},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4759102463722229},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4546819031238556},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4501051604747772},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.44641247391700745},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4426332116127014},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.4274233281612396},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41024741530418396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3655768036842346},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3571838140487671},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.33322304487228394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8350245952606201},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7372204065322876},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6050679683685303},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5589120388031006},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.5560511946678162},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5501837730407715},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.49196740984916687},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.49116751551628113},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4759102463722229},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4546819031238556},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4501051604747772},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.44641247391700745},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4426332116127014},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4274233281612396},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41024741530418396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3655768036842346},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3571838140487671},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.33322304487228394},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3490099.3511164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3490099.3511164","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3490099.3511164","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"27th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3490099.3511164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3490099.3511164","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3490099.3511164","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"27th International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3177739361","display_name":null,"funder_award_id":"21J20353","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5622405347","display_name":"\u4efb\u610f\u30c4\u30fc\u30eb\u3067\u306e\u30c7\u30b6\u30a4\u30f3\u652f\u63f4\u306e\u305f\u3081\u306eGAN\u3092\u7528\u3044\u305f\u30b5\u30f3\u30d7\u30eb\u6a21\u5023\u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af","funder_award_id":"22KJ0353","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5888469927","display_name":null,"funder_award_id":"JPMJAX200R, JPMJCR20D4","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220793814.pdf"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W28755848","https://openalex.org/W272928725","https://openalex.org/W587099658","https://openalex.org/W1119960297","https://openalex.org/W1527177318","https://openalex.org/W1531049516","https://openalex.org/W1544682780","https://openalex.org/W1576919282","https://openalex.org/W1876657623","https://openalex.org/W1970026646","https://openalex.org/W1977757124","https://openalex.org/W1987810558","https://openalex.org/W1997178453","https://openalex.org/W2010910318","https://openalex.org/W2050968192","https://openalex.org/W2078922236","https://openalex.org/W2129120544","https://openalex.org/W2143562645","https://openalex.org/W2157289187","https://openalex.org/W2170101331","https://openalex.org/W2183100634","https://openalex.org/W2329223578","https://openalex.org/W2505877856","https://openalex.org/W2610697282","https://openalex.org/W2621461883","https://openalex.org/W2627092829","https://openalex.org/W2741188008","https://openalex.org/W2796141464","https://openalex.org/W2801659857","https://openalex.org/W2912581782","https://openalex.org/W2942475617","https://openalex.org/W2962780374","https://openalex.org/W2963785710","https://openalex.org/W2973216307","https://openalex.org/W2981910996","https://openalex.org/W3009398997","https://openalex.org/W3020336359","https://openalex.org/W3030958012","https://openalex.org/W3046415477","https://openalex.org/W3086154751","https://openalex.org/W3097777922","https://openalex.org/W3098557217","https://openalex.org/W3109931032","https://openalex.org/W3196843354","https://openalex.org/W4241408685","https://openalex.org/W4249399411","https://openalex.org/W4399236360"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W4312668661","https://openalex.org/W2105439218","https://openalex.org/W3151376046","https://openalex.org/W2355899496","https://openalex.org/W3089379469","https://openalex.org/W2903652364","https://openalex.org/W430347950","https://openalex.org/W2147630093","https://openalex.org/W642007152"],"abstract_inverted_index":{"Transcribing":[0],"speech":[1,33,38,72,79,82,140,231],"from":[2,201,251],"audio":[3,16],"files":[4],"to":[5,31,49,107,122,179,199,266,286],"text":[6,19],"is":[7,74,164,167,176,291],"an":[8,104,149],"important":[9],"task":[10,172],"not":[11,75],"only":[12],"for":[13,23,77,125,158,193,270,294],"exploring":[14],"the":[15,25,51,61,93,113,138,189,244,252,255,258,288,298],"content":[17],"in":[18,60,128,282],"form":[20],"but":[21],"also":[22],"utilizing":[24],"transcribed":[26],"data":[27],"as":[28,36,81,141],"a":[29,133,168,181,239,264,301],"source":[30],"train":[32],"models,":[34],"such":[35],"automated":[37],"recognition":[39,62],"(ASR)":[40],"models.":[41,66],"A":[42],"post-correction":[43],"approach":[44,69,106,154,241],"has":[45,118],"been":[46,120],"frequently":[47],"employed":[48],"reduce":[50],"time":[52],"cost":[53],"of":[54,64,86,95,115,229,246,257,300],"transcription":[55,271],"where":[56],"users":[57,198],"edit":[58],"errors":[59],"results":[63],"ASR":[65,96,150],"However,":[67],"this":[68,153,185],"assumes":[70],"clear":[71],"and":[73,97,143,173,212,260],"designed":[76,192],"unclear":[78,109,160,230],"(such":[80],"with":[83,187,235,238,297],"high":[84],"levels":[85],"noise":[87],"or":[88],"reverberation),":[89],"which":[90,117],"severely":[91],"degrades":[92],"accuracy":[94,245],"requires":[98],"many":[99],"manual":[100],"corrections.":[101],"To":[102],"construct":[103],"alternative":[105],"transcribe":[108,226],"speech,":[110,161],"we":[111,277],"introduce":[112],"idea":[114],"respeaking,":[116,132],"primarily":[119],"used":[121],"create":[123],"captions":[124],"television":[126],"programs":[127],"real":[129],"time.":[130],"In":[131,248],"proficient":[134],"human":[135],"respeaker":[136],"repeats":[137],"heard":[139],"shadowing,":[142],"their":[144],"utterances":[145],"are":[146],"recognized":[147],"by":[148],"model.":[151],"While":[152],"can":[155,278],"be":[156],"effective":[157],"transcribing":[159],"one":[162],"problem":[163],"that":[165,195,223,290],"respeaking":[166,194,202],"highly":[169],"cognitively":[170],"demanding":[171],"extensive":[174,204],"training":[175,205],"often":[177],"required":[178],"become":[180],"respeaker.":[182],"We":[183],"address":[184],"point":[186],"BeParrot,":[188],"first":[190],"interface":[191],"allows":[196],"novice":[197],"benefit":[200],"without":[203,242],"through":[206],"two":[207],"key":[208],"features:":[209],"parameter":[210],"adjustment":[211,259],"pronunciation":[213],"feedback.":[214],"Our":[215,273],"user":[216],"study":[217],"involving":[218],"60":[219],"crowd":[220],"workers":[221,253],"demonstrated":[222],"they":[224],"could":[225],"different":[227],"types":[228],"32.2":[232],"%":[233],"faster":[234],"BeParrot":[236,269],"than":[237],"conventional":[240],"losing":[243],"transcriptions.":[247],"addition,":[249],"comments":[250],"supported":[254],"design":[256],"feedback":[261],"features,":[262],"exhibiting":[263],"willingness":[265],"continue":[267],"using":[268],"tasks.":[272],"work":[274],"demonstrates":[275],"how":[276],"leverage":[279],"recent":[280],"advances":[281],"machine":[283],"learning":[284],"techniques":[285],"overcome":[287],"area":[289],"still":[292],"challenging":[293],"computers":[295],"themselves":[296],"help":[299],"human-in-the-loop":[302],"approach.":[303]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}